Machine learning-based radiomic, clinical and semantic feature analysis for predicting overall survival and MGMT promoter methylation status in patients with glioblastoma.

Survival varies in patients with glioblastoma due to intratumoral heterogeneity and radiomics/imaging biomarkers have potential to demonstrate heterogeneity. The objective was to combine radiomic, semantic and clinical features to improve prediction of overall survival (OS) and O A retrospective study of 181 MRI studies (mean age 58 ± 13 years, mean OS 497 ± 354 days) performed in patients with histopathology-proven glioblastoma. Tumour mass, contrast-enhancement and necrosis were segmented from volumetric contrast-enhanced T1-weighted imaging (CE-T1WI). 333 radiomic features were extracted and 16 Visually Accessible Rembrandt Images (VASARI) features were evaluated by two experienced neuroradiologists. Top radiomic, VASARI and clinical features were used to build machine learning models to predict MGMT status, and all features including MGMT status were used to build Cox proportional hazards regression (Cox) and random survival forest (RSF) models for OS prediction. The optimal cut-off value for MGMT promoter methylation index was 12.75%; 42 radiomic features exhibited significant differences between high and low-methylation groups. However, model performance accuracy combining radiomic, VASARI and clinical features for MGMT status prediction varied between 45 and 67%. For OS predication, the RSF model based on clinical, VASARI and CE radiomic features achieved the best performance with an average iAUC of 96.2 ± 1.7 and C-index of 90.0 ± 0.3. VASARI features in combination with clinical and radiomic features from the enhancing tumour show promise for predicting OS with a high accuracy in patients with glioblastoma from pre-operative volumetric CE-T1WI.

Informations de copyright

Copyright © 2020 Elsevier Inc. All rights reserved.